11 June 2024 Symmetric image compression network with improved normalization attention mechanism
Shen-Chuan Tai, Chia-Mao Yeh, Yu-Ting Lee, Wesley Huang
Author Affiliations +
Abstract

Image compression plays a vital role in various applications, such as the storage, transmission, and sharing of digital images. We present a symmetric image compression that leverages improved normalization and attention mechanisms to achieve superior compression performance. We focus on addressing the limitations of conventional normalization techniques in handling diverse image characteristics effectively. An adaptive normalization module is proposed to adjust normalization parameters dynamically based on the content of the input image; it ensures optimal data representation and contributes to improved compression efficiency. Furthermore, a windowed attention mechanism is integrated into the compression network to selectively focus on significant image regions while suppressing noise and redundancies by effectively capturing and preserving important visual features to enhance the overall compression quality and reconstruction fidelity. Comparative analysis with state-of-the-art methods demonstrates the superiority of the proposed symmetric image compression network in terms of compression ratio, reconstruction quality, and subjective visual perception. Moreover, the effects of different normalization and attention configurations on compression performance are thoroughly investigated and analyzed. The results of the experiments validate the effectiveness of the proposed symmetric image compression network with improved normalization and windowed attention, known as the Image Compression Attention Normalization Network. The integration of adaptive normalization and windowed attention mechanisms not only enhances the compression efficiency but also enables adaptability to diverse image characteristics. The proposed compression scheme results are as follows. The inference time for encoding and decoding is 0.152 and 0.163 s, respectively. The Bjøntegaard delta (BD) rate shows a reduction of 74.8936%, and the BD-peak signal-to-noise ratio increases by 6.425 dB. The computational load is measured in floating-point operations and totals 263.614G, with the model utilizing 68.1M parameters. Windowed attention preserves critical data, and adaptive normalization alters image processing, enhancing ablation studies. Despite differences, both modules contribute to emphasizing data retention and adjustments and optimizing image processing for improved results.

© 2024 SPIE and IS&T
Shen-Chuan Tai, Chia-Mao Yeh, Yu-Ting Lee, and Wesley Huang "Symmetric image compression network with improved normalization attention mechanism," Journal of Electronic Imaging 33(3), 033028 (11 June 2024). https://doi.org/10.1117/1.JEI.33.3.033028
Received: 29 January 2024; Accepted: 22 May 2024; Published: 11 June 2024
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Image compression

Image quality

Image enhancement

Image restoration

Image processing

Windows

Distortion

RELATED CONTENT

Image resizing enhancement with DCT coefficients
Proceedings of SPIE (January 31 2020)
Perceptually lossless fractal image compression
Proceedings of SPIE (February 27 1996)
Region-based DCT image coding scheme
Proceedings of SPIE (June 03 1997)

Back to Top